Daniel Kang

Breaking Barriers: Do Reinforcement Post Training Gains Transfer To Unseen Domains?

BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Trigger Learning

Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation

MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Knowledge Poisoning Attacks

Chart2CSV: Can VLMs Faithfully Convert Complex Charts into Structured Tables?

CVE-Bench: A Benchmark for AI Agents’ Ability to Exploit Real-World Web Application Vulnerabilities

Evaluating Model Robustness Against Unforeseen Adversarial Attacks